AgentDB

What it does

Vector memory with no server to keep running: a single .rvf file holds the embeddings and the CLI exposes it over MCP. The appeal is portability — commit the file, copy it between machines, diff it. Recall quality is entirely a function of what you store, and nothing stops you from storing noise.

Install

npx agentdb mcp start

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

{
  "mcpServers": {
    "agentdb": {
      "command": "npx",
      "args": [
        "agentdb",
        "mcp",
        "start"
      ]
    }
  }
}

When to use it

Reach for this when the task needs memory inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

• Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
• Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
• Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude